CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aislop-sweep

Thin Codex skill shim for node_aislop_sweep. Use when scanning OmniNode repos for AI-generated quality anti-patterns or AI slop.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/onex/skills/aislop-sweep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers a highly actionable, well-sectioned dispatch procedure with an explicit preflight validation step and clear error surfacing. Its weaknesses are moderate duplication between the generated runtime-truth block and the Contract section, a placeholder payload with no worked example, and the inlining of transport contract metadata that could live in a reference file.

Suggestions

Deduplicate the Contract section against the generated Runtime truth block (command name, command topic, and terminal topic are repeated verbatim); keep only the backing-node path and wrapper reference there.

Add one concrete example of the '<json-payload>' JSON (e.g., {"target_dirs": ["/abs/repo"], "checks": [...], "severity_threshold": "WARNING"}) so the dispatch command is copy-paste ready.

Move the verbose transport/evidence metadata (wire schema details, binding fields, topic tables) into a single one-level-deep reference file, leaving a short pointer in SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly efficient — no explanation of concepts Claude already knows — but the "Runtime truth" block and the "Contract" section repeat the same command name and topics verbatim ("aislop_sweep", "onex.cmd.omnimarket.aislop-sweep-start.v1", "onex.evt.omnimarket.aislop-sweep-completed.v1"), and ~40 lines of transport/evidence metadata are inlined. This fits the "mostly efficient but could be tightened" anchor; it is above the verbose anchor because there is no padding or filler, only duplication.

3 / 5

Actionability

Provides a concrete, runnable dispatch command ("env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name \"aislop_sweep\" ..."), an explicit argument-to-JSON payload mapping, a defaults table, and a failure rule ("If `ok` is `false`, surface `error.code` and `error.message`"). Mostly executable with a minor gap: the payload is a '<json-payload>' placeholder with no worked example, which keeps it below the fully copy-paste-ready anchor.

4 / 5

Workflow Clarity

A clear section-ordered sequence (Arguments → Dispatch → Output) with an explicit validation checkpoint ("For event-bus-free preflight, add `--compile-only`. This validates the payload, command topic, response topic, correlation id, timeout, and target runtime address") and a defined failure path. Below the top anchor because the sequence is implicit rather than numbered and there is no error-recovery/retry guidance; the scan is read-only reporting with a dry-run option, so the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist and the body is cleanly sectioned (Arguments, Dispatch, Contract, Output), but at ~110 lines the sub-50-line simple-skill exception does not strictly apply, and the dense generated transport metadata (topics, evidence wire schema, binding fields) is a plausible candidate for a one-level-deep reference file. This fits "good structure; minor organization gaps" — above the "content that should be separate is inline" anchor because the structure is clean and nothing is buried, below the top anchor because the bulky contract metadata is fully inlined.

4 / 5

Total

15

/

20

Passed

Description

73%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, distinct description with an explicit "Use when" clause and natural trigger terms like "AI slop". Its main weakness is that the "what" is expressed through internal jargon (shim/node naming) and only one concrete action, rather than plainly stating the operations the skill performs.

DimensionReasoningScore

Specificity

Names the domain ("Thin Codex skill shim for node_aislop_sweep") and one concrete action ("scanning OmniNode repos for AI-generated quality anti-patterns or AI slop"), but does not enumerate the shim's own operations (argument collection, dispatch, result rendering). This matches the anchor for domain plus 1-2 concrete actions without comprehensive coverage; it is above the minimal/generic-actions anchor because scanning for AI slop is a specific, concrete action.

3 / 5

Completeness

Both parts are present: the "what" ("Thin Codex skill shim for node_aislop_sweep") and an explicit "Use when scanning OmniNode repos for AI-generated quality anti-patterns or AI slop" trigger clause, so the missing-Use-when cap does not apply. Not a 5 because the "what" leans on internal jargon ("thin Codex skill shim", the node name) rather than plainly stating the operation; the "when" is explicit and reasonably specific.

4 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — "AI slop", "AI-generated", "anti-patterns", "scanning" — giving good keyword coverage. Not a 5 because common synonyms and variations such as "LLM-generated code" or "slop detection" are missing; not a 3 because the primary natural trigger terms are all present.

4 / 5

Distinctiveness Conflict Risk

"AI slop" / "AI-generated quality anti-patterns" scanning scoped to OmniNode repos is a clear niche with distinct trigger phrases; minimal risk of firing for the wrong skill, matching the top anchor.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

OmniNode-ai/omnimarket

Path

plugins/onex/skills/aislop-sweep/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.